incident-report
Pass
Audited by Gen Agent Trust Hub on Sep 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted data regarding production incidents, including commands, logs, and technical descriptions (Phase 2 in SKILL.md). If this data contains malicious instructions, the agent might follow them during the report generation phase.
- Ingestion points: Phase 2: Core Facts, Technical Details, and Impact Assessment inputs collected from the user or external systems.
- Boundary markers: Absent. The instructions do not specify delimiters or warnings to ignore instructions embedded within the technical details or log samples.
- Capability inventory: The skill primarily performs file-write operations (generating markdown reports) based on the templates in
templates/. - Sanitization: Not present. There is no mention of escaping, filtering, or validating the input data before it is interpolated into the markdown templates.
- [CREDENTIALS_UNSAFE]: While not directly exfiltrating credentials, the templates in
templates/client-report.mdandtemplates/internal-report.mdencourage the user to include sensitive details like 'Affected data types', 'Exposure scope', and 'WhatsApp/Email' contact info. If misused or if the agent context is compromised, this could lead to inadvertent exposure of private contact details or specific security vulnerabilities.
Audit Metadata